Papers by Haoyu Yang

24 papers
EmoMM: Benchmarking and Steering MLLM for Multimodal Emotion Recognition under Conflict and Missingness (2026.findings-acl)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) have shown promise in MER, but their internal decision-making mechanisms under modality conflict and missingness remain underexplored.
Approach: They propose a multimodal large language model that can detect and control modality conflicts and missing subsets by a lightweight mechanism that detects and controls modality conflict.
Outcome: The proposed framework improves performance across settings, showing it can handle conflict and missing behaviors.
Defending against Indirect Prompt Injection by Instruction Detection (2025.findings-emnlp)

Copied to clipboard

Challenge: Indirect Prompt Injection attacks can be exploited by LLMs that are embedded with external data.
Approach: They propose a detection-based approach that leverages the behavioral states of LLMs to identify potential IPI attacks.
Outcome: The proposed approach reduces the success rate of attacks to 0.03% on the BIPIA benchmark.
MAIN: Mutual Alignment Is Necessary for instruction tuning (2025.emnlp-main)

Copied to clipboard

Challenge: Instruction tuning has enabled large language models to achieve remarkable performance, yet its success heavily depends on the availability of high-quality instruction-response pairs.
Approach: They propose a mutual alignment framework which enforces coherence between instructions and responses through mutual constraints.
Outcome: The proposed framework generalizes well across model architectures and sizes, achieving state-of-the-art performance on LLaMA, Mistral, and Qwen models across diverse benchmarks.
Out-of-Domain Detection for Low-Resource Text Classification Tasks (D19-1)

Copied to clipboard

Challenge: Existing methods for OOD detection and ID classification tasks require massive amounts of ID labeled data and no OOD labeles.
Approach: They propose to use OOD-resistant Prototypical Network to detect OOD cases with limited in-domain (ID) training data to solve this task.
Outcome: The proposed solution outperforms state-of-the-art methods in zero-shot OOD detection task while maintaining a competitive performance on ID classification task.
AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios (2025.naacl-long)

Copied to clipboard

Challenge: Large language models are increasingly employed to empower autonomous agents to simulate human behavior.
Approach: They propose to evaluate LLM-driven agents through multi-turn interactions using a bottom-up approach to create diverse social scenarios constructed from extensive scripts.
Outcome: The proposed model evaluates LLM-driven agents through multi-turn interactions emphasizing goal completion and implicit reasoning.
Dual-Reasoner: Bridging Interleaved Atomicity and Streaming Latency via Thinking-while-Talking (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods to integrate Chain-of-Thought into spoken dialogue models incur prohibitive latency.
Approach: They propose a Streaming Masking Mechanism to ensure uninterrupted audio streaming . they use a quadruple-constraint system to reconstruct logical atomicity .
Outcome: Experimental results show that Dual-Reasoner improves speech generation performance with low latency.
Speech-Text Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment (2023.acl-long)

Copied to clipboard

Challenge: Existing speech-text pre-training methods are limited to one or two specific tasks, despite their success in speech-language processing tasks.
Approach: They propose a temporal position prediction task to capture the speech-text alignment . they use a textual dialog pre-training task to generalize a response selection task .
Outcome: The proposed model is superior in learning speech-text alignment and multi-turn dialog context.
Can LLMs be Good Graph Judge for Knowledge Graph Construction? (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for converting unstructured text into structured Knowledge Graphs (KGs) have limitations such as large amount of noise, inaccurate knowledge, and hallucination .
Approach: They propose a GraphJudge framework to reduce noise in real-world documents . they propose Graphjudge to fine-tune a LLM as a graph judge to enhance quality .
Outcome: The proposed framework eliminates noise in real-world documents and improves the quality of generated KGs.
AI-Press: A Multi-Agent News Generating and Feedback Simulation System Powered by Large Language Models (2025.coling-demos)

Copied to clipboard

Challenge: We introduce AI-Press, an automated news drafting and polishing system based on multi-agent collaboration and Retrieval-Augmented Generation.
Approach: They introduce AI-Press, an automated news drafting and polishing system based on multi-agent collaboration and Retrieval-Augmented Generation.
Outcome: The proposed system generates public responses considering demographic distributions.
Efficient and Effective Prompt Tuning via Prompt Decomposition and Compressed Outer Product (2025.naacl-long)

Copied to clipboard

Challenge: Existing methods for fine-tuning pre-trained language models overlook intrinsic semantic associations between soft prompt tokens, leading to high discreteness and limited interactions.
Approach: They propose a low-parameters Prompt Tuning method which leverages prompt decomposition and compressed outer product to facilitate multiple interactions among prompt tokens.
Outcome: Experiments on six architectures and eight datasets show that the proposed method outperforms state-of-the-art methods in performance and efficiency.
AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora (2026.acl-long)

Copied to clipboard

Challenge: Existing knowledge graph construction frameworks require predefined schemas, limiting their scalability and domain coverage.
Approach: They propose a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas.
Outcome: The proposed framework outperforms state-of-the-art models on multi-hop QA tasks and enhances LLM factuality.
Knowledge Decoupling via Orthogonal Projection for Lifelong Editing of Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for enhancing large language models (LLMs) have achieved some success, but their knowledge understanding and memory capacity significantly degrades after extensive editing.
Approach: They propose a method that stores the basis vectors of the representation space of past edits in a knowledge cache and projects the gradient of the current edit onto a space orthogonal to previous knowledge for updating.
Outcome: The proposed method improves question-answering ability and hallucination mitigation by 14% and 61% for large language models after 3,000 edits.
Retrieval-Augmented Generation with Hierarchical Knowledge (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing RAG methods do not utilize hierarchical knowledge in human cognition, which limits the capabilities of RAG systems.
Approach: They propose a graph-based approach that utilizes hierarchical knowledge to enhance the semantic understanding and structure capturing capabilities of RAG systems.
Outcome: The proposed approach achieves significant performance improvements over the state-of-the-art methods.
STAF: Pushing the Boundaries of Test-Time Adaptation towards Practical Noise Scenarios (2024.lrec-main)

Copied to clipboard

Challenge: Pre-trained language models have demonstrated superior performance on NLP tasks . however, when the training domain and testing domain are taken from different distributions, the deployed model often violates this assumption.
Approach: They propose a Stable Test-time Adaptation Framework to stabilize the adaptation process.
Outcome: The proposed framework boosts model robustness to noise distribution shifts while minimizing error accumulation and catastrophic forgetting.
Devil’s Advocate: Anticipatory Reflection for LLM Agents (2024.findings-emnlp)

Copied to clipboard

Challenge: Introspection-driven approach equips LLM agents with introspection, enhancing consistency and adaptability in solving complex tasks.
Approach: They propose a zero-shot approach that equips LLM agents with introspection, enhancing consistency and adaptability in solving complex tasks.
Outcome: The proposed approach improves performance and efficiency by reducing the number of trials and plan revisions by 45%.
Evaluating the Expressive Appropriateness of Speech in Rich Contexts (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for evaluating expressive speech focus on word accuracy, naturalness, signal quality, or emotional intensity at the utterance level.
Approach: They propose a framework for Evaluating Expressive Appropriateness in speech that assesses whether a speech sample aligns with the underlying communicative intent implied by its discourse-level narrative context.
Outcome: The proposed framework outperforms existing speech evaluation and analysis systems on a human-annotated test set.
Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have achieved great success in various NLP tasks, but the vast model parameters pose challenges in downstream fine-tuning.
Approach: They propose a task-agnostic prompting strategy that analyzes each dialogue utterance before task execution to enhance LLMs' comprehension in multi-turn dialogues.
Outcome: The proposed strategy outperforms other zero-shot prompts and matches or exceeds efficacy of few-shot ones.
UltraLink: An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset (2024.acl-long)

Copied to clipboard

Challenge: Open-source large language models (LLMs) have gained strength across diverse fields, but the majority of studies focus on English.
Approach: They propose a knowledge-grounded data augmentation approach to elicit more language-specific knowledge of LLMs by enhancing their ability to serve users from different countries.
Outcome: The proposed method can prune the language-agnostic supervised fine-tuning dataset without any performance degradation.
RAM2C: A Liberal Arts Educational Chatbot based on Retrieval-augmented Multi-role Multi-expert Collaboration (2025.coling-main)

Copied to clipboard

Challenge: Empirical evaluations indicate that RAM2C-empowered LLMs excel in Chinese reading teaching, offering more personalized, and ethically safe teaching response.
Approach: They propose a framework to retrieve large language models into educational dialogues and organize them into multi-experts groups with distinct roles to generate the data.
Outcome: Empirical evaluations show that RAM2C-empowered LLMs excel in Chinese reading teaching, offering more personalized, and ethically safe teaching response.
OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment (2026.acl-long)

Copied to clipboard

Challenge: Existing reward models rely on scalar or pairwise judgments that fail to capture multifaceted nature of human preferences.
Approach: They propose a rubric-based reward model that uses a large collection of prompt, rubric pairs to generate a scalar score or preference label for each response.
Outcome: The proposed model surpasses strong size-matched baselines by 8.4% across multiple benchmarks.
Can Large Language Models Tackle Graph Partitioning? (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have remarkable capabilities in understanding complex tasks, but they can only handle graph partitioning tasks that require global perception abilities.
Approach: They propose a pipeline for coarsening, reasoning, and refining to enable LLMs to perform graph partitioning on small-scale graphs.
Outcome: The proposed pipeline can handle graph partitioning tasks on small graphs with coarsening, reasoning, and refining.
RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation (2026.findings-acl)

Copied to clipboard

Challenge: Retrieval-augmented generation (RAG) enhances large language models by integrating external knowledge retrieved at inference time.
Approach: They evaluate RAG systems using MassiveDS, a large-scale datastore with mixture of knowledge.
Outcome: The proposed approach improves performance on knowledge-intensive NLP tasks.
Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated remarkable success across a wide range of tasks, however, they still face challenges in reasoning tasks that require understanding and inferring relationships between distinct pieces of information within text sequences.
Approach: They propose to construct explicit graphs from context and leverage them to enhance LLM reasoning performance on reasoning tasks.
Outcome: Extensive experiments show that the proposed method improves both logical reasoning and multi-hop question answering tasks.
MPR-GUI: Benchmarking and Enhancing Multilingual Perception and Reasoning in GUI Agents (2026.acl-long)

Copied to clipboard

Challenge: Existing GUI benchmarks lack fine-grained diagnostics to identify which capabilities lead to task failures.
Approach: They propose a multilingual P R GUI Benchmark to assess LVLMs' language capabilities . they propose XLI to align non-English hidden states with English ones during inference .
Outcome: The proposed benchmark reveals consistent gaps between English and non-English settings . it reduces the cross-lingual gaps with an average gain of 6.5% in non- English settings compared to static benchmarks .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations